© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 20771
    Prev
    Next
    INDEX
    Explanations

    dates or locations of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "held" related to events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clerosis
    -0.66
    ————
    -0.65
     deceive
    -0.65
     omission
    -0.63
    kes
    -0.59
     Daylight
    -0.59
     Plain
    -0.58
    include
    -0.58
     adventurer
    -0.58
     bandits
    -0.57
    POSITIVE LOGITS
     accountable
    1.04
     hostage
    1.03
     captive
    0.92
    DOWN
    0.78
    erness
    0.78
    overs
    0.75
     Held
    0.75
     vigil
    0.71
    ĸļ
    0.71
    hold
    0.70
    Activations Density 0.037%

    No Known Activations